INDEX

Explanations

instances where something is given or provided to someone

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "given" in various contexts

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

ansas

-0.72

tenance

-0.71

Ark

-0.67

ater

-0.67

Phoenix

-0.64

 Strait

-0.61

tra

-0.61

velt

-0.61

trak

-0.61

itect

-0.59

POSITIVE LOGITS

aways

0.85

enced

0.80

 precedence

0.80

bread

0.79

 refunds

0.79

 permission

0.79

ãĥį

0.79

ãĥ¯

0.77

 preferential

0.76

 priority

0.75

Activations Density 0.044%

instances where something is given or provided to someone

occurrences of the word "given" in various contexts

No Comments

No Known Activations