INDEX

Explanations

specific noun phrases related to actions or situations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 horizont

-0.66

anwhile

-0.63

 surrounds

-0.58

":["

-0.57

ãĤ´ãĥ³

-0.56

 Signed

-0.56

rants

-0.54

rought

-0.54

 throats

-0.54

 Gret

-0.54

POSITIVE LOGITS

 impression

0.82

 leap

0.75

sense

0.72

 distinction

0.71

 mistake

0.66

 distinctions

0.66

 determin

0.65

 debut

0.64

 difference

0.63

yssey

0.63

Activations Density 0.119%

specific noun phrases related to actions or situations

occurrences of the word "the."

No Comments

No Known Activations