INDEX

Explanations

phrases or words related to gaining entry or obtaining information

oai_token-act-pair · gpt-3.5-turbo

instances of the word "access" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

fare

-0.66

balls

-0.65

warming

-0.61

break

-0.60

 abst

-0.59

yes

-0.58

cas

-0.58

inning

-0.58

ignore

-0.58

 stint

-0.57

POSITIVE LOGITS

ibly

1.10

ibility

0.98

IBLE

0.88

ible

0.85

ãĥ¼ãĥĨãĤ£

0.79

ioned

0.77

ibles

0.77

folios

0.77

ADRA

0.77

éŃĶ

0.73

Activations Density 0.040%

phrases or words related to gaining entry or obtaining information

instances of the word "access" and its variations

No Comments

No Known Activations