INDEX

Explanations

verbs describing actions or decisions influenced by choices, such as 'waiting', 'relying', 'trying', 'silence', 'confronting', and 'recognizing'

oai_token-act-pair · gpt-3.5-turbo

phrases indicating alternative actions or approaches

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rongh

-0.68

quad

-0.68

bon

-0.66

marked

-0.64

added

-0.64

 Adin

-0.63

perty

-0.63

mma

-0.63

 Âł Âł Âł Âł

-0.62

rolet

-0.62

POSITIVE LOGITS

 blindly

0.81

 altogether

0.77

 excuses

0.76

 anymore

0.75

 outright

0.74

udicrous

0.74

 passively

0.71

 anything

0.69

 simplistic

0.67

 inconvenient

0.65

Activations Density 0.159%

verbs describing actions or decisions influenced by choices, such as 'waiting', 'relying', 'trying', 'silence', 'confronting', and 'recognizing'

phrases indicating alternative actions or approaches

No Comments

No Known Activations