INDEX

Explanations

verbs related to changes in contracts or agreements

oai_token-act-pair · gpt-3.5-turbo

terms related to the cancellation or reversal of agreements or decisions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enne

-0.83

achine

-0.72

 Plenty

-0.72

inki

-0.69

hidden

-0.69

hov

-0.69

istics

-0.68

ust

-0.68

 cooled

-0.66

 starved

-0.66

POSITIVE LOGITS

 eligibility

0.90

 decision

0.90

 judgment

0.90

 judgement

0.87

 sanctions

0.82

 decree

0.82

 longstanding

0.81

 decisions

0.80

 reservation

0.80

 validity

0.80

Activations Density 0.232%

verbs related to changes in contracts or agreements

terms related to the cancellation or reversal of agreements or decisions

No Comments

No Known Activations