INDEX

Explanations

phrases related to literal interpretations or descriptions

oai_token-act-pair · gpt-3.5-turbo

distinctions between literal and figurative language

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

reau

-0.76

Crash

-0.74

pered

-0.73

edu

-0.72

Rated

-0.69

angan

-0.66

afety

-0.66

meet

-0.66

sponsored

-0.66

Recommend

-0.66

POSITIVE LOGITS

orical

0.97

 literal

0.87

 figur

0.85

 Meaning

0.83

orically

0.79

 meanings

0.79

ãĤ¨ãĥ«

0.79

TY

0.78

 meaning

0.78

 interpretation

0.75

Activations Density 0.020%

phrases related to literal interpretations or descriptions

distinctions between literal and figurative language

No Comments

No Known Activations